import pandas as pd
from sklearn.model_selection import train_test_split, cross_val_score, StratifiedKFold
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, precision_score, recall_score, f1_score
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
from sklearn.svm import SVC
import joblib
# Veri setini yükle
data = pd.read_csv('touchstandard.csv')
# Bağımsız değişkenler ve hedef değişkeni ayır
X = df.drop(columns=["user_id", "touch_type", "touch", "finger", "palm", "fist"])
y = df["user_id"]
models = {
"Naive Bayes": GaussianNB(),
"Random Forest": RandomForestClassifier(),
"SVM": SVC()
}
def evaluate_model(model, X, y):
cv = StratifiedKFold(n_splits=10, shuffle=True, random_state=47)
scores = cross_val_score(model, X, y, scoring="accuracy", cv=cv)
return scores.mean()
results = {}
# Evaluate models, split the dataset, and print both mean accuracy and test accuracy
for name, model in models.items():
# Split the dataset for testing
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=47, stratify=y)
# Evaluate the model using cross-validation
mean_accuracy = evaluate_model(model, X_train, y_train)
# Train the model on the training set
model.fit(X_train, y_train)
# Calculate the test accuracy
test_accuracy = model.score(X_test, y_test)
results[name] = test_accuracy
# Print both mean accuracy and test accuracy
print(f"{name} cross-validation mean accuracy score:", mean_accuracy)
print(f"{name} test accuracy score:", test_accuracy)
# Select the best performing model based on mean accuracy
best_model = max(results, key=results.get)
print("Best performing model based on test accuracy:", best_model)
# Split the dataset for testing using the best model with specified random seed and stratification
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=47, stratify=y)
# Train the best model
best_model_instance = models[best_model]
best_model_instance.fit(X_train, y_train)
# Evaluate the performance of the best model on the test set
test_accuracy = best_model_instance.score(X_test, y_test)
print("Test set accuracy score (best model):", test_accuracy)
# Calculate evaluation metrics for the best model
y_pred = best_model_instance.predict(X_test)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')
# Print the evaluation metrics for the best model
print("\nEvaluation metric scores for best model which is {}:".format(best_model))
print("Test set accuracy:", test_accuracy)
print("Test set precision:", precision)
print("Test set recall:", recall)
print("Test set F1 score:", f1)
joblib.dump(best_model, 'best_model_isedataset_classification.pkl')
